Simulated EIT circular targets with noise and blur

Companion data for the paper "Post-processing electrical impedance tomography reconstructions with incomplete data using convolutional neural networks".

See https://github.com/robert-abc/KTC2023-ABC1 for more information. 

Files:

CNN_input.mat: CNN input, the noisy data

CNN_output.mat: CNN output, the clean data

cnn_training.py: Describes the CNN training using Keras

CNN_training.ipynb: Notebook after the CNN training

ultimate_cnn1.h5: CNN (keras) file after training

We uploaded the files to Google Drive and executed the code using Google Colab.

Before executing the code, one should change the current working directory to the folder where the files are.